implement an optimization to codegen c ? 1.0 : 2.0 as load { 2.0, 1.0 } + c*4.

For 2009-03-07-FPConstSelect.ll we now produce:

_f:
	xorl	%eax, %eax
	testl	%edi, %edi
	movl	$4, %ecx
	cmovne	%rax, %rcx
	leaq	LCPI1_0(%rip), %rax
	movss	(%rcx,%rax), %xmm0
	ret

previously we produced:

_f:
	subl	$4, %esp
	cmpl	$0, 8(%esp)
	movss	LCPI1_0, %xmm0
	je	LBB1_2	## entry
LBB1_1:	## entry
	movss	LCPI1_1, %xmm0
LBB1_2:	## entry
	movss	%xmm0, (%esp)
	flds	(%esp)
	addl	$4, %esp
	ret

on PPC the code also improves to:

_f:
	cntlzw r2, r3
	srwi r2, r2, 5
	li r3, lo16(LCPI1_0)
	slwi r2, r2, 2
	addis r3, r3, ha16(LCPI1_0)
	lfsx f1, r3, r2
	blr 

from:

_f:
	li r2, lo16(LCPI1_1)
	cmplwi cr0, r3, 0
	addis r2, r2, ha16(LCPI1_1)
	beq cr0, LBB1_2	; entry
LBB1_1:	; entry
	li r2, lo16(LCPI1_0)
	addis r2, r2, ha16(LCPI1_0)
LBB1_2:	; entry
	lfs f1, 0(r2)
	blr 

This also improves the existing pic-cpool case from:

foo:
	subl	$12, %esp
	call	.Lllvm$1.$piclabel
.Lllvm$1.$piclabel:
	popl	%eax
	addl	$_GLOBAL_OFFSET_TABLE_ + [.-.Lllvm$1.$piclabel], %eax
	cmpl	$0, 16(%esp)
	movsd	.LCPI1_0@GOTOFF(%eax), %xmm0
	je	.LBB1_2	# entry
.LBB1_1:	# entry
	movsd	.LCPI1_1@GOTOFF(%eax), %xmm0
.LBB1_2:	# entry
	movsd	%xmm0, (%esp)
	fldl	(%esp)
	addl	$12, %esp
	ret

to:

foo:
	call	.Lllvm$1.$piclabel
.Lllvm$1.$piclabel:
	popl	%eax
	addl	$_GLOBAL_OFFSET_TABLE_ + [.-.Lllvm$1.$piclabel], %eax
	xorl	%ecx, %ecx
	cmpl	$0, 4(%esp)
	movl	$8, %edx
	cmovne	%ecx, %edx
	fldl	.LCPI1_0@GOTOFF(%eax,%edx)
	ret

This triggers a few dozen times in spec FP 2000.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@66358 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 12 insertions, 0 deletions

diff --git a/test/CodeGen/X86/2009-03-07-FPConstSelect.ll b/test/CodeGen/X86/2009-03-07-FPConstSelect.ll
new file mode 100644
index 0000000000..28302c0f7b
--- /dev/null
+++ b/test/CodeGen/X86/2009-03-07-FPConstSelect.ll
@@ -0,0 +1,12 @@
+; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah | not grep xmm
+; This should do a single load into the fp stack for the return, not diddle with xmm registers.
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
+target triple = "i386-apple-darwin7"
+
+define float @f(i32 %x) nounwind readnone {
+entry:
+	%0 = icmp eq i32 %x, 0		; <i1> [#uses=1]
+	%iftmp.0.0 = select i1 %0, float 4.200000e+01, float 2.300000e+01
+	ret float %iftmp.0.0
+}